Aiper MCP server for AI agents
Let Claude, ChatGPT or your own agent read Aiper: 2 typed functions through one MCP server. No Aiper API key needed.
- Site
- aiper.store
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Aiper
An MCP server for Aiper alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/aiperEvery site
One MCP server for Aiper and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
listPoolChooserQuestionsLists the questions the Help Me Choose pool-cleaner finder asks (pool size, surface, shape, areas to clean, priorities), each with its option labels.Arguments
None.
Returns
AiperPoolQuestion[]interface AiperPoolOption { id: string; label: string; } interface AiperPoolQuestion { id: string; problemName: string; multiSelect: boolean; options: AiperPoolOption[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/aiper/listPoolChooserQuestionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.aiper.listPoolChooserQuestions();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.aiper.listPoolChooserQuestions())curl -X POST https://api.bowmark.ai/v1/sites/aiper/listPoolChooserQuestions \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.aiper.listPoolChooserQuestions();recommendPoolCleanerRuns the Help Me Choose quiz's real backend computation against a buyer's answers and returns the computed recommended model(s).Arguments
Name Type Required answersAiperPoolAnswerInput[]Yes interface AiperPoolAnswerInput { question: string; choice: string | string[]; }Returns
AiperPoolRecommendationinterface AiperPoolAnswerInput { question: string; choice: string | string[]; } interface AiperRecommendedProduct { productId: string; slug: string; name: string; sku: string; price: number; regularPrice: number; url: string; image: string | null; } interface AiperPoolRecommendation { products: AiperRecommendedProduct[]; answers: AiperPoolAnswerInput[]; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/aiper/recommendPoolCleanerCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.aiper.recommendPoolCleaner([]);import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.aiper.recommendPoolCleaner([]))curl -X POST https://api.bowmark.ai/v1/sites/aiper/recommendPoolCleaner \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"answers":[]}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.aiper.recommendPoolCleaner([]);
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/aiper/<function> - OpenAPI
/v1/sites/aiper/openapi.json